Including Transfer Learning and Synthetic Data in a Training Process of a 2D Object Detector for Autonomous Driving.
Miguel AntunesLuis Miguel BergasaJavier AraluceRodrigo GutiérrezJuan Felipe ArangoManuel OcañaPublished in: ROBOT (2) (2022)
Keyphrases
- d objects
- synthetic data
- training process
- transfer learning
- autonomous driving
- grand challenge
- training data
- labeled data
- stereo vision
- viewpoint
- multi view
- object recognition
- semi supervised learning
- semi supervised
- reinforcement learning
- cross domain
- data sets
- active learning
- vision algorithms
- three dimensional
- neural network
- real image data
- pose estimation
- transfer knowledge
- real world
- unlabeled data
- text classification
- machine learning
- multiple views
- urban traffic
- multi task
- collaborative filtering
- support vector machine
- text categorization
- learning algorithm
- target domain
- text mining
- computer vision
- machine learning algorithms
- stereo matching
- multimedia
- data mining
- training examples
- learning process
- image sequences